© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 38313
    Prev
    Next
    INDEX
    Explanations

    references to academic or athletic achievements and records

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ibold
    -0.07
    America
    -0.07
    Stencil
    -0.06
    Americ
    -0.06
    imb
    -0.06
    bill
    -0.06
    wb
    -0.06
     Sap
    -0.06
    rup
    -0.06
    ãĥ§
    -0.06
    POSITIVE LOGITS
    .records
    0.08
     records
    0.08
     record
    0.07
     lifetime
    0.07
     Records
    0.07
    è®°å½ķ
    0.07
    oser
    0.07
     RECORD
    0.07
    records
    0.07
    arken
    0.07
    Activations Density 0.011%

    No Known Activations